INDEX

Explanations

references to real-life events and situations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

istrovstvÃŃ

-0.17

xfb

-0.15

etxt

-0.14

iant

-0.14

iales

-0.14

YYS

-0.14

conds

-0.14

cept

-0.14

Ã©ric

-0.14

stvo

-0.13

POSITIVE LOGITS

 counterpart

0.18

imony

0.16

eco

0.15

gear

0.15

 counterparts

0.15

bat

0.14

 augment

0.14

like

0.14

 occurrences

0.14

.opensource

0.14

Activations Density 0.046%

references to real-life events and situations

No Comments

No Known Activations